research-grants

Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/research-grants/SKILL.md

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is well-structured with strong progressive disclosure and concrete, actionable agency-specific facts. It is somewhat verbose in places (agency missions, generic common mistakes) and the workflow lacks explicit validation feedback loops.

Suggestions

Trim or remove the per-agency 'Mission' lines and condense the 25-item 'Common Mistakes' list to grant-specific pitfalls to reduce token overhead.

Add an explicit validation/verification checkpoint in the submission phase (e.g. 'Run a compliance checklist against page limits and required sections before uploading') with a fix-and-retry loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete agency facts, but includes padding Claude already knows (per-agency 'Mission' lines) and a lengthy, fairly generic 'Common Mistakes' section (25 items) that could be trimmed.	3 / 5
Actionability	Concrete, specific guidance abounds — page limits ('15-page project description', 'Specific Aims (1 page)'), form names (CM03, PAPPG 24-1), and an executable schematic command — with only minor high-level directions in the workflow.	4 / 5
Workflow Clarity	Five sequenced phases with timeframes, Activities, and Outputs give a clear sequence with deliverable checkpoints and submission verification, though explicit validate-then-proceed feedback loops are only lightly present.	4 / 5
Progressive Disclosure	The body is a clear overview with well-signaled, one-level-deep references (core_components.md, review_criteria.md, per-agency guidelines) and assets, all verified to exist, making navigation easy.	5 / 5
	Total	16 / 20 Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and highly distinctive, enumerating concrete grant-writing actions and named agencies. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when writing or revising grant proposals for NSF, NIH, DOE, DARPA, or Taiwan NSTC, or when responding to a solicitation or summary statement.'

Include common user synonyms such as 'grants', 'funding proposals', 'solicitations', and mechanism names (e.g. R01) to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	It clearly states the 'what' (writing proposals with enumerated sub-tasks) but provides no 'Use when...' clause or explicit trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Agency names (NSF, NIH, DOE, DARPA, NSTC) and 'research proposals' are natural terms users say, but common synonyms like 'grants', 'funding', 'solicitations', and mechanism names (e.g. R01) are missing.	4 / 5
Distinctiveness Conflict Risk	Naming five specific funding agencies carves out a clear niche with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/research-grants/SKILL.md
Commit: b2a92ba

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.